© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41527
    Prev
    Next
    INDEX
    Explanations

    process data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammers
    -0.07
    ¶
    -0.07
    å·¥å§Ķ
    -0.07
    ÙİÙĬ
    -0.07
    ä¸įçĦ¶
    -0.07
    缸åħ³å·¥ä½ľç»ıéªĮ
    -0.06
    ertz
    -0.06
    åľ¨äºĨåľ°ä¸Ĭ
    -0.06
    oria
    -0.06
    ä¸ĢæĪIJ
    -0.06
    POSITIVE LOGITS
    åĴĮå¤ĦçIJĨ
    0.12
    è¿ĩçļĦ
    0.12
    éģİçļĦ
    0.10
    лÑĭк
    0.08
    /respond
    0.08
    åĴĮä¿ĿæĬ¤
    0.08
    éĢIJ个
    0.08
    åĴĮæĶ¯æĮģ
    0.07
    -worthy
    0.07
    ahan
    0.07
    Activations Density 0.031%

    No Known Activations